社会科学及相邻学科学术写作与选题论证工作台，覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断言与概念混用。也适用于开题报告、研究计划书、学位论文的选题…
$ npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-social-science --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nature-social-science .claude/skills/nature-social-science && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "nature-social-science" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-science into .claude/skills/nature-social-science/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-social-science", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-scienceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-social-science --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nature-social-science .agents/skills/nature-social-science && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nature-social-science" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-science into .agents/skills/nature-social-science/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-social-science", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-social-science --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nature-social-science .cursor/skills/nature-social-science && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nature-social-science" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-science into .cursor/skills/nature-social-science/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-social-science", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Yuan1z0825/nature-skills.git --path skills/nature-social-science--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-social-science --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nature-social-science .gemini/skills/nature-social-science && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nature-social-science" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-science into .gemini/skills/nature-social-science/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-social-science", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Yuan1z0825/nature-skills nature-social-scienceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nature-social-science .github/skills/nature-social-science && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nature-social-science" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-science into .github/skills/nature-social-science/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-social-science", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Yuan1z0825/nature-skills nature-social-science --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nature-social-science .opencode/skills/nature-social-science && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nature-social-science" agent skill from https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-social-science into .opencode/skills/nature-social-science/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nature-social-science", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
nature-social-science社会科学及相邻学科学术写作与选题论证工作台，覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断言与概念混用。也适用于开题报告、研究计划书、学位论文的选题…
Nature Social Science is an agent skill from Yuan1z0825/nature-skills. 社会科学及相邻学科学术写作与选题论证工作台，覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断言与概念混用。也适用于开题报告、研究计划书、学位论文的选题阶段与论证自检。
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including reference files (for example `README.md`, `README_EN.md` and `agents/openai.yaml`).
The repository describes itself as: 符合nature论文学术表达和科研绘图的Skill. The licence is Apache-2.0.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e605b35. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Nature Social Science loads about 1.6k tokens when it runs, and up to ~58k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 484 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Yuan1z0825/nature-skills at commit e605b35, republished under its Apache-2.0 licence (© Yuan1z0825). 484 words, ~1,608 tokens.
.claude/skills/nature-social-science/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.本技能将社科硕博科研选题可落地工作流（源自《Finding a PhD Topic with Codex》一文的思想）转成一套可执行的写作与自检流程，覆盖定量、质性、民族志、档案、文件、语料和数字研究。
适用范围：社会科学及相邻人文学科。定量、质性、民族志、档案、文件、语料和数字研究都能用。 判断标准始终相同：问题是否清楚，证据是否匹配，主张是否诚实，项目是否能由这名研究者完成。
不做什么：不替你生成一个"正确题目"，不保证新颖、录取、资助、发表或论文成功， 不把某种方法当作高质量研究的默认答案。AI 的自信不是证据；填完的表格不是通关证明。
| 用户诉求 | 对应要素 | 走哪几步 | 读哪些参考 |
|---|---|---|---|
| "我想研究 XX"／"帮我找个论文题目" | 选题构思 | Step 1 → 2 → 3 | 01-foundations.md、02-workflow-steps1-3.md |
| "这方向有人做过吗"／文献怎么梳理／版图怎么画 | 文献梳理 | Step 2 → 3 | 02-workflow-steps1-3.md |
| "我有数据/我想用方法 M" | 选题构思（假起点） | 先回 Step 1 | 01-foundations.md §六 Two false starts |
| "这个题目能不能做"／证据够不够 | 论证组织 + 可行性 | Step 4 → 7 | 03-workflow-steps4-5.md、04-workflow-steps6-8.md |
| "帮我生成几个研究问题"／RQ 怎么写 | 选题构思 | Step 5 | 03-workflow-steps4-5.md |
| "帮我想想审稿人会怎么攻击"／查新颖性 | 论证组织 | Step 6 | 04-workflow-steps6-8.md |
| "结论是不是说过头了"／表述定级 | 学术表达 | Step 4 的 claim ceiling + 术语纪律 | 09-academic-expression.md、07-status-terminology.md |
| "帮我改稿／润色论证段落" | 学术表达 | 对照 claim ceiling 与 Red flags | 09-academic-expression.md |
| "怎么跟导师谈"／开题材料怎么写 | 交付使用 | Part III | 08-usage-handoff.md |
| 需要现成提示词 | — | 按步骤取 | 05-prompt-library.md（唯一权威版本） |
| 需要填表模板 | — | 按步骤取 | 06-worksheets.md |
入口判断（必做第一步）：只有兴趣 → Mode A；已有宽泛主题或关系 → Mode B； 已有暂定研究问题 → Mode C（audit route，不是 advanced route）。 只有数据集或方法偏好时，先问"它能帮助理解什么未决现象"，答不出来从 Mode A 开始。
Current Research State，不要把整段旧对话带进下一步。配套禁止项（写进每一次给出的提示词里）：
任何一次关于选题或论证的判断，先过这张表。完整版见 01-foundations.md §四。
| 不要混为一谈 | 可操作的检查 |
|---|---|
| Interest ≠ Topic | 是否已经划出要探索的现象、过程和边界？ |
| Topic ≠ Research problem | 是否指出领域中具体哪里解释不通？ |
| Research problem ≠ Research question | 是否把知识困难变成可由证据推进的任务？ |
| Research gap ≠ "few studies" | 研究少造成了什么知识后果？ |
| Novelty ≠ nobody has studied it | 是否解决矛盾、机制、测量或新近可回答的问题？ |
| Interesting ≠ Important | 除了个人兴趣，答案会改变谁对什么的理解？ |
| Important ≠ Answerable | 是否有合适、合规且时间匹配的证据？ |
| Available source ≠ Valid evidence | 字段、文本或观察真的对应目标概念吗？ |
| Correlation ≠ Mechanism | 是否看见过程，还是只看见现象同时出现？ |
| Advanced method ≠ Strong contribution | 方法是否解决了原来的知识困难？ |
| Feasible study ≠ PhD-worthy project | 它能否支撑一个核心谜题与连贯发展？ |
| AI judgement ≠ Researcher judgement | 哪些决定需要用户的价值、经验和导师判断？ |
| Step | 主产物 | 决策问题 | Gate |
|---|---|---|---|
| 1. Research Search Space | 一页搜索空间 | 概念与边界是否足以搜索？ | PASS / REVISE / STOP |
| 2. Research Landscape | 领域版图 | 是否看见多种问题、解释和反证？ | 同上 |
| 3. Unresolved Problems | 3–7 个问题卡 | 是否存在有后果的知识不确定性？ | 同上 |
| 4. Evidence Map | 1–3 条证据路线 | 是否能观察核心问题并守住主张上限？ | 同上 |
| 5. Candidate RQs | 6–12 张候选卡 | 是否有实质不同、可被攻击的问句？ | 同上（起用 PARK） |
| 6. Academic Survival | Novelty Audit + Reviewer 2 | 候选是否经学术攻击仍存活？ | 同上 |
| 7. PhD Feasibility | 可行性档案 | 是否没有未处理硬失败，且能发展成博士？ | 同上 |
| 8. Final Shortlist | 最多三张 Topic Cards | 能否清楚说明取舍和下一项核实？ | 同上 |
Step 5 会短暂扩展候选、随后收窄，这不是纯线性管道。
回退规则：若设计只能提供弱代理、错误单位或不合适时间 → 返回 Question； 若连问题的知识后果也消失 → 返回 Problem。
| 在问什么 | 用哪套 | 取值 |
|---|---|---|
| 我能进入下一步吗？ | Workflow Gate | PASS / REVISE / STOP（+ PARK） |
| 这条证据路线核实到哪了？ | Evidence State | NAMED / DOCUMENTED / ACCESS-CONFIRMED / TESTED |
| 这条候选经学术攻击后怎样？ | Academic Survival | SURVIVE / REDESIGN / PARK / REJECT |
| 这项硬条件现在什么状态？ | PhD Feasibility Dependency | CONFIRMED / RESOLVABLE DEPENDENCY / UNKNOWN / FAIL |
| 这条候选能进最终比较吗？ | PhD Feasibility Disposition | PROCEED TO COMPARISON / REDESIGN / PARK / REJECT |
六条不许抹平的不等式：
UNKNOWN ≠ PASS — 未知需要核实动作，不是乐观解释。DOCUMENTED ≠ ACCESS-CONFIRMED — 官方文件说来源存在，不等于用户已满足资格、许可、地点、费用和伦理条件。SURVIVE ≠ novel — 通过一次有界攻击，不等于证明全世界没有近似研究。PARK ≠ bad idea — 缺的是决定性证据或条件，不是想法本身。PASS ≠ permanent approval — 新文献、访问变化、伦理意见、实测结果都可能把它变成 REVISE 或 STOP。REJECT ≠ wasted work — 拒绝记录保存了最近似工作、失败条件和边界，能阻止以后重复同一错误。不要创建"综合状态"。 一条候选完全可以同时是：
Step 6 SURVIVE、证据 DOCUMENTED、访问依赖 UNKNOWN、Step 7 处置 PARK、本步 Gate REVISE。
这些标签并不矛盾，它们回答不同问题。详见 07-status-terminology.md。
05-prompt-library.md 找到对应 prompt，只准备 Required input；06-worksheets.md 里的对应表格，不把长对话当作最终记录；Current Research State，再按 08-usage-handoff.md 进入下一步或暂时退出。上下文控制：每次转段只带 Carry forward 的内容，主动丢弃 Leave behind。
08-usage-handoff.md 给出了九次交接各自该带什么、丢什么、哪项判断必须由用户作出、
以及哪类未知会阻塞推进。
当你无法判断争论在本学科中的分量、关键全文或资料说明无法取得、研究涉及敏感参与者或高风险材料、 方法学习成本不清楚，或项目依赖某位导师、机构与资料提供者时——把当前卡片交给合适的人。
AI 可以帮你准备问题，不能替他们授权。
需要交给真人的典型场景与方法，见 08-usage-handoff.md 与 01-foundations.md §五「什么时候找真人」。
05-prompt-library.md 中的提示词为逐字保留原件，正文里自称"我正在使用 Codex"。
直接复制即可；若在别的 agent 里使用，可把 Codex 替换为当前助手的名字，其余一字不改。05-prompt-library.md。各步骤文件里的"短预览"只作说明，不要另造一版并行维护。06-worksheets.md 的对应表格与 Current Research State。以下九个文件均位于本 skill 的 references/ 目录下，按需只读当前步骤需要的那个。
| 文件 | 内容 |
|---|---|
01-foundations.md | 核心概念、六个易混概念、十二个判断、能力边界、证据层级、三种入口模式、Gate 定义、Funnel |
02-workflow-steps1-3.md | Step 1 搜索空间 / Step 2 领域版图（文献梳理核心）/ Step 3 未决问题 |
03-workflow-steps4-5.md | Step 4 证据地图与 claim ceiling / Step 5 候选研究问题 |
04-workflow-steps6-8.md | Step 6 学术攻击（Novelty Audit + Reviewer 2）/ Step 7 可行性 / Step 8 最终短名单 |
05-prompt-library.md | 全部可复制提示词（唯一权威版本） |
06-worksheets.md | 11 份工作表模板 |
07-status-terminology.md | 五套状态系统 + 术语小词典 + Current Research State |
08-usage-handoff.md | 短名单使用、导师沟通、九次交接、恢复规则 |
09-academic-expression.md | 学术表达纪律：主张上限、动词与证据相称、诚实措辞句式表、各步 Red flags（起草与改稿时必读） |
使用时只做四件事：不知道的写"未知"；要求找反证；保留证据层级与失败记录；每步更新状态表。
© Yuan1z0825, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 13 other files (references) in skills/nature-social-science of Yuan1z0825/nature-skills.
Open the folder on GitHubat commit e605b35
franklee16/academic-research-skills
基于同一项研究的研究目的、研究问题、理论框架与人群设计，协同产出彼此对齐的量化问卷/调查表和质性访谈提纲时使用；也可在用户明确要求时把经审核的问卷创建为问卷星未发布草稿并继续管理。触发信号包括“问卷和访谈一起设计”“根据研究思路同步出调查问卷与访谈提纲”“混合方法研究工具”“不同人群分别做问卷和访谈”“推送到问卷星”“创建在线问卷”“survey + interview…
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
Yuan1z0825/nature-skills
Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.
Yuan1z0825/nature-skills
Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.
Yuan1z0825/nature-skills
Composes, revises or audits research proposals and opening reports through an evidence-first state machine with argument maps, section contracts and dynamic expert reviewers.
Yuan1z0825/nature-skills
Routes literature requests to lawful full-text sources: open access, publisher APIs, CNKI and institutional browser access, with a supporting-information gate.
Yuan1z0825/nature-skills
Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA.
社会科学及相邻学科学术写作与选题论证工作台，覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断言与概念混用。也适用于开题报告、研究计划书、学位论文的选题…. Nature Social Science is an agent skill from Yuan1z0825/nature-skills.
Run `npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a claude-code`. Or copy the skill folder (skills/nature-social-science in Yuan1z0825/nature-skills) into .claude/skills/nature-social-science in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a codex`. Or copy the skill folder (skills/nature-social-science in Yuan1z0825/nature-skills) into .agents/skills/nature-social-science in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yuan1z0825/nature-skills --skill nature-social-science -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nature-social-science, .gemini/skills/nature-social-science, .github/skills/nature-social-science and .opencode/skills/nature-social-science in your project.
SKILL.md names no scripts, command-line tools or credentials: Nature Social Science is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Nature Social Science is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 56k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Nature Social Science: Mixed Methods Instrument Design (franklee16/academic-research-skills, 223 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Yuan1z0825 (a GitHub user) maintains it in Yuan1z0825/nature-skills, which has 47,222 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 11, 2026.
Source: Yuan1z0825/nature-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
